jpayne@69: #!/bin/bash
jpayne@69: 
jpayne@69: usage(){
jpayne@69: echo "
jpayne@69: Written by Brian Bushnell
jpayne@69: Last modified January 28, 2020
jpayne@69: 
jpayne@69: Description:  Merges files of SSU sequences to keep one per taxID.
jpayne@69: By default, a consensus is generated per TaxID, then the sequence
jpayne@69: best matching that consensus is used:
jpayne@69: First, all sequences per TaxID are aligned to a reference consensus.
jpayne@69: Second, the best-matching sequence is used as a seed, and all other
jpayne@69: sequences for that TaxID are aligned to the seed to generate a new consensus.
jpayne@69: Third, in 'consensus' mode, that consensus is simply output.
jpayne@69: In 'best' mode (default), all sequences are aligned again to the new consensus,
jpayne@69: and the best-matching is output.
jpayne@69: 
jpayne@69: Usage:  mergeribo.sh in=<file,file> out=<file> 16S
jpayne@69: 
jpayne@69: Standard parameters:
jpayne@69: in=<file,file>  Comma-delimited list of files.
jpayne@69: out=<file>      Output file.
jpayne@69: out2=<file>     Read 2 output if reads are in two files.
jpayne@69: overwrite=f     (ow) Set to false to force the program to abort rather than
jpayne@69:                 overwrite an existing file.
jpayne@69: showspeed=t     (ss) Set to 'f' to suppress display of processing speed.
jpayne@69: ziplevel=2      (zl) Set to 1 (lowest) through 9 (max) to change compression
jpayne@69:                 level; lower compression is faster.
jpayne@69: 
jpayne@69: Processing parameters:
jpayne@69: alt=<file>      Lower priority data.  Only used if there is no SSU associated
jpayne@69:                 with the TaxID from the primary input.
jpayne@69: best=t          Output the best representative per taxID.
jpayne@69: consensus=f     Output a consensus per taxID instead of the best input
jpayne@69:                 sequence.  Mutually exclusive with best.
jpayne@69: fast=f          Output the best sequence based on alignment to global consensus
jpayne@69:                 (the seed) rather than individual consensus.
jpayne@69: minid=0.62      Ignore sequences with identity lower than this to the global
jpayne@69:                 consensus.
jpayne@69: maxns=-1        Ignore sequences with more than this many Ns, if non-negative.
jpayne@69: minlen=1        Ignore sequences shorter than this.
jpayne@69: maxlen=4000     Ignore sequences longer than this.
jpayne@69: 16S=t           Align to 16S consensus to pick the seed. Mutually exclusive.
jpayne@69: 18S=f           Align to 18S consensus to pick the seed. Mutually exclusive.
jpayne@69: 
jpayne@69: Java Parameters:
jpayne@69: -Xmx            This will set Java's memory usage, overriding autodetection.
jpayne@69:                 -Xmx20g will specify 20 gigs of RAM, and -Xmx200m will
jpayne@69:                 specify 200 megs. The max is typically 85% of physical memory.
jpayne@69: -eoom           This flag will cause the process to exit if an out-of-memory
jpayne@69:                 exception occurs.  Requires Java 8u92+.
jpayne@69: -da             Disable assertions.
jpayne@69: 
jpayne@69: Please contact Brian Bushnell at bbushnell@lbl.gov if you encounter any problems.
jpayne@69: "
jpayne@69: }
jpayne@69: 
jpayne@69: #This block allows symlinked shellscripts to correctly set classpath.
jpayne@69: pushd . > /dev/null
jpayne@69: DIR="${BASH_SOURCE[0]}"
jpayne@69: while [ -h "$DIR" ]; do
jpayne@69:   cd "$(dirname "$DIR")"
jpayne@69:   DIR="$(readlink "$(basename "$DIR")")"
jpayne@69: done
jpayne@69: cd "$(dirname "$DIR")"
jpayne@69: DIR="$(pwd)/"
jpayne@69: popd > /dev/null
jpayne@69: 
jpayne@69: #DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" && pwd )/"
jpayne@69: CP="$DIR""current/"
jpayne@69: 
jpayne@69: z="-Xmx4g"
jpayne@69: z2="-Xms4g"
jpayne@69: set=0
jpayne@69: 
jpayne@69: if [ -z "$1" ] || [[ $1 == -h ]] || [[ $1 == --help ]]; then
jpayne@69: 	usage
jpayne@69: 	exit
jpayne@69: fi
jpayne@69: 
jpayne@69: calcXmx () {
jpayne@69: 	source "$DIR""/calcmem.sh"
jpayne@69: 	setEnvironment
jpayne@69: 	parseXmx "$@"
jpayne@69: 	if [[ $set == 1 ]]; then
jpayne@69: 		return
jpayne@69: 	fi
jpayne@69: 	freeRam 4000m 42
jpayne@69: 	z="-Xmx${RAM}m"
jpayne@69: 	z2="-Xms${RAM}m"
jpayne@69: }
jpayne@69: calcXmx "$@"
jpayne@69: 
jpayne@69: mergeribo() {
jpayne@69: 	local CMD="java $EA $EOOM $z -cp $CP prok.MergeRibo $@"
jpayne@69: 	echo $CMD >&2
jpayne@69: 	eval $CMD
jpayne@69: }
jpayne@69: 
jpayne@69: mergeribo "$@"